基于多尺度密集连接网络的电容层析成像图像重建OA北大核心CSTPCD
Image Reconstruction of Electrical Capacitance Tomography Based on Multi-scale Densely Connected Network
为求解电容层析成像中的非线性病态反问题,提出了一种多尺度密集连接网络(MD-Net)模型.该模型由多尺度特征融合模块和密集连接块组成,以通过融合多尺度特征进一步提高图像的重建精度.通过MATLAB仿真实验平台构建了流型数据集,利用密集连接网络的非线性映射能力,完成训练集的学习与训练,并利用测试集进行训练效果评价.在此基础上进行了静态实验.仿真与静态实验结果均表明:与LBP、Landweber迭代算法和其他深度学习方法相比,该方法的重建精度最高、抗…查看全部>>
In order to solve the nonlinear ill-posed inverse problem in electrical capacitance tomography(ECT),a multiscale dense connection network(multi-scale densely connected network,MD-Net)model is proposed.The model consists of a multiscale feature fusion module and a densely connected block to further improve the reconstruction accuracy of images by fusing multiscale features.A flow-type data set is constructed by the MATLAB simulation experiment platform,and th…查看全部>>
张立峰;常恩健
华北电力大学自动化系,河北保定 071003华北电力大学自动化系,河北保定 071003
两相流测量电容层析成像图像重建深度学习密集连接网络
two-phase flow measurementelectrical capacitance tomographyimage reconstructiondeep learningdensely connected network
《计量学报》 2024 (5)
678-684,7
国家自然科学基金(61973115)
评论